Add model weights

chat_template.json

@@ -0,0 +1 @@
+{"chat_template": "{%- set ns = namespace(system_text=\"\") -%}\n{%- for m in messages -%}\n  {%- if m.role == 'system' -%}\n    {%- if m.content is string -%}\n      {%- set ns.system_text = ns.system_text + m.content -%}\n    {%- else -%}\n      {%- for c in m.content -%}\n        {%- if c.type == 'text' and (c.text is defined) -%}\n          {%- set ns.system_text = ns.system_text + c.text -%}\n        {%- endif -%}\n      {%- endfor -%}\n    {%- endif -%}\n  {%- endif -%}\n{%- endfor -%}\n\n{%- set ns2 = namespace(audio_tokens=\"\") -%}\n{%- for m in messages -%}\n  {%- if m.content is not string -%}\n    {%- for c in m.content -%}\n      {%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}\n        {%- set ns2.audio_tokens = ns2.audio_tokens + \"<|audio_start|><|audio_pad|><|audio_end|>\" -%}\n      {%- endif -%}\n    {%- endfor -%}\n  {%- endif -%}\n{%- endfor -%}\n\n{{- '<|im_start|>system\\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\\n' -}}\n{{- '<|im_start|>user\\n' + ns2.audio_tokens + '<|im_end|>\\n' -}}\n{%- if add_generation_prompt -%}\n{{- '<|im_start|>assistant\\n' -}}\n{%- endif -%}"}

config.json

@@ -0,0 +1,221 @@
+{
+    "architectures": [
+      "Qwen3ASRForConditionalGeneration"
+    ],
+    "model_type": "qwen3_asr",
+    "support_languages": [
+      "Chinese",
+      "English",
+      "Cantonese",
+      "Arabic",
+      "German",
+      "French",
+      "Spanish",
+      "Portuguese",
+      "Indonesian",
+      "Italian",
+      "Korean",
+      "Russian",
+      "Thai",
+      "Vietnamese",
+      "Japanese",
+      "Turkish",
+      "Hindi",
+      "Malay",
+      "Dutch",
+      "Swedish",
+      "Danish",
+      "Finnish",
+      "Polish",
+      "Czech",
+      "Filipino",
+      "Persian",
+      "Greek",
+      "Romanian",
+      "Hungarian",
+      "Macedonian"
+    ],
+    "thinker_config": {
+      "model_type": "qwen3_asr",
+      "architectures": [
+        "Qwen3ASRForConditionalGeneration"
+      ],
+      "audio_config": {
+        "_name_or_path": "",
+        "activation_dropout": 0,
+        "activation_function": "gelu",
+        "add_cross_attention": false,
+        "architectures": null,
+        "attention_dropout": 0,
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": null,
+        "chunk_size_feed_forward": 0,
+        "conv_chunksize": 500,
+        "cross_attention_hidden_size": null,
+        "d_model": 1024,
+        "decoder_start_token_id": null,
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "downsample_hidden_size": 480,
+        "dropout": 0,
+        "dtype": null,
+        "early_stopping": false,
+        "encoder_attention_heads": 16,
+        "encoder_ffn_dim": 4096,
+        "encoder_layers": 24,
+        "encoder_no_repeat_ngram_size": 0,
+        "eos_token_id": null,
+        "exponential_decay_length_penalty": null,
+        "finetuning_task": null,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "id2label": {
+          "0": "LABEL_0",
+          "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+          "LABEL_0": 0,
+          "LABEL_1": 1
+        },
+        "length_penalty": 1.0,
+        "max_length": 20,
+        "max_source_positions": 1500,
+        "min_length": 0,
+        "model_type": "qwen3_asr_audio_encoder",
+        "n_window": 50,
+        "n_window_infer": 800,
+        "no_repeat_ngram_size": 0,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_hidden_layers": 24,
+        "num_mel_bins": 128,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_dim": 2048,
+        "output_hidden_states": false,
+        "output_scores": false,
+        "pad_token_id": null,
+        "prefix": null,
+        "problem_type": null,
+        "pruned_heads": {},
+        "remove_invalid_values": false,
+        "repetition_penalty": 1.0,
+        "return_dict": true,
+        "return_dict_in_generate": false,
+        "scale_embedding": false,
+        "sep_token_id": null,
+        "suppress_tokens": null,
+        "task_specific_params": null,
+        "temperature": 1.0,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": true,
+        "tokenizer_class": null,
+        "top_k": 50,
+        "top_p": 1.0,
+        "torchscript": false,
+        "typical_p": 1.0,
+        "use_bfloat16": false
+      },
+      "audio_end_token_id": 151670,
+      "audio_start_token_id": 151669,
+      "audio_token_id": 151676,
+      "dtype": "bfloat16",
+      "initializer_range": 0.02,
+      "text_config": {
+        "_name_or_path": "",
+        "add_cross_attention": false,
+        "architectures": null,
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "bad_words_ids": null,
+        "begin_suppress_tokens": null,
+        "bos_token_id": null,
+        "chunk_size_feed_forward": 0,
+        "cross_attention_hidden_size": null,
+        "decoder_start_token_id": null,
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "dtype": null,
+        "early_stopping": false,
+        "encoder_no_repeat_ngram_size": 0,
+        "eos_token_id": null,
+        "exponential_decay_length_penalty": null,
+        "finetuning_task": null,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "head_dim": 128,
+        "hidden_act": "silu",
+        "hidden_size": 2048,
+        "id2label": {
+          "0": "LABEL_0",
+          "1": "LABEL_1"
+        },
+        "initializer_range": 0.02,
+        "intermediate_size": 6144,
+        "is_decoder": false,
+        "is_encoder_decoder": false,
+        "label2id": {
+          "LABEL_0": 0,
+          "LABEL_1": 1
+        },
+        "length_penalty": 1.0,
+        "max_length": 20,
+        "max_position_embeddings": 65536,
+        "min_length": 0,
+        "model_type": "qwen3",
+        "no_repeat_ngram_size": 0,
+        "num_attention_heads": 16,
+        "num_beam_groups": 1,
+        "num_beams": 1,
+        "num_hidden_layers": 28,
+        "num_key_value_heads": 8,
+        "num_return_sequences": 1,
+        "output_attentions": false,
+        "output_hidden_states": false,
+        "output_scores": false,
+        "pad_token_id": null,
+        "prefix": null,
+        "problem_type": null,
+        "pruned_heads": {},
+        "remove_invalid_values": false,
+        "repetition_penalty": 1.0,
+        "return_dict": true,
+        "return_dict_in_generate": false,
+        "rms_norm_eps": 1e-06,
+        "rope_scaling": {
+          "interleaved": true,
+          "mrope_interleaved": true,
+          "mrope_section": [
+            24,
+            20,
+            20
+          ],
+          "rope_type": "default",
+          "type": "default"
+        },
+        "rope_theta": 1000000,
+        "sep_token_id": null,
+        "suppress_tokens": null,
+        "task_specific_params": null,
+        "temperature": 1.0,
+        "tf_legacy_loss": false,
+        "tie_encoder_decoder": false,
+        "tie_word_embeddings": true,
+        "tokenizer_class": null,
+        "top_k": 50,
+        "top_p": 1.0,
+        "torchscript": false,
+        "typical_p": 1.0,
+        "use_bfloat16": false,
+        "use_cache": true,
+        "vocab_size": 151936
+      }
+    },
+    "transformers_version": "4.57.6"
+  }
+  

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": [151643,151645],
+  "pad_token_id": 151643,
+  "do_sample": false,
+  "temperature": 0.000001
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4cd1f1a04d90b757dc7f7dd26254e69a013b19e80efe590a83c6a3bde8608d6
+size 4220320824

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0b9d9e09e2e0238e7ef3cc8a484ab387e91b90f1900bedf88bc92d7929ccfc
+size 478200688

model.safetensors.index.json

@@ -0,0 +1,715 @@
+{
+  "metadata": {
+    "format": "pt"
+  },
+  "weight_map": {
+    "thinker.audio_tower.conv2d1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.conv2d1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.conv2d2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.conv2d2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.conv2d3.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.conv2d3.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.conv_out.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.0.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.1.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.10.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.4.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.5.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.6.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.7.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.8.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.fc1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.fc1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.fc2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.layers.9.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.ln_post.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.ln_post.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.proj1.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.proj1.weight": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.proj2.bias": "model-00001-of-00002.safetensors",
+    "thinker.audio_tower.proj2.weight": "model-00001-of-00002.safetensors",
+    "thinker.lm_head.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "thinker.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.5.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "thinker.model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "dither": 0.0,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Qwen3ASRProcessor",
+  "return_attention_mask": true
+}

tokenizer_config.json

@@ -0,0 +1,549 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<non_speech>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151676": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151677": {
+      "content": "<blank1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151678": {
+      "content": "<blank2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151679": {
+      "content": "<blank3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "<blank4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151681": {
+      "content": "<blank5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151682": {
+      "content": "<blank6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151683": {
+      "content": "<blank7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151684": {
+      "content": "<blank8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151685": {
+      "content": "<blank9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151686": {
+      "content": "<blank10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151687": {
+      "content": "<blank11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151688": {
+      "content": "<blank12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151689": {
+      "content": "<blank13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151690": {
+      "content": "<blank14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151691": {
+      "content": "<blank15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151692": {
+      "content": "<blank16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151693": {
+      "content": "<blank17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151694": {
+      "content": "<blank18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151695": {
+      "content": "<blank19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151696": {
+      "content": "<blank20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151697": {
+      "content": "<blank21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151698": {
+      "content": "<blank22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151699": {
+      "content": "<blank23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151700": {
+      "content": "<blank24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151701": {
+      "content": "<blank25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151702": {
+      "content": "<blank26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151703": {
+      "content": "<blank27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151704": {
+      "content": "<asr_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_bos_single>",
+    "<|audio_pad|>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "image_token": "<|image_pad|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3ASRProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}